Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horizontally
    -0.06
     efect
    -0.06
    丁目
    -0.06
    ruz
    -0.06
    'D
    -0.06
    ादन
    -0.06
    莫
    -0.06
     Rear
    -0.06
     万円
    -0.06
    	elseif
    -0.05
    POSITIVE LOGITS
    (one
    0.07
     Cork
    0.07
     paths
    0.06
    wave
    0.06
     Pero
    0.06
     interracial
    0.06
    _managed
    0.06
     Canadiens
    0.06
     ATF
    0.06
     linebacker
    0.06
    Act Density 0.005%

    No Known Activations